Hello,

On Tue, Dec 21, 2010 at 12:20:00PM -0800, David Miller wrote:
quoted text
> From: Tejun Heo <tj@kernel.org>
> Date: Tue, 21 Dec 2010 11:51:04 +0100
> 
> > Yeah, I agree the synchronize_rcu() there would guarantee the actual
> > timer completion but as it currently stands it looks a bit too subtle.
> > Maybe it's a good idea to add a big fat comment explaining that the
> > the timer is guaranteed to stop after close() and how it's guaranteed
> > through synchronize_rcu() at the moment?  Also, it might be better to
> > use synchronize_sched() there as timer synchronization through
> > synchronize_rcu() is more of a happy accident.
> 
> I'm not sure the synchronize_*() is even necessary to guarentee
> watchdog timer completion.
> 
> Like I said, I think the netif_tx_lock() held around both the timer
> function itself, and the del_timer() call, are sufficient.
> 
> So, this ensures that the watchdog timer either runs to completion or
> sees the no-op scheduler attached and returns immediately without
> rescheduling the timer.
> 
> In any event, I'm going to apply your bnx2 patch to net-next-2.6

Oh, yeah, all is good if the timer is guaranteed to stop after close
one way or the other.  Thanks and happy new year!

-- 
tejun
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/